Optimized routing of interactions to contact center agents based on forecast agent availability and customer patience

• US 9,723,151 B2
• Filed: 10/19/2015
• Issued: 08/01/2017
• Est. Priority Date: 10/19/2015
• Status: Active Grant

• Current Assignee: Genesys Cloud Services Incorporated
• Original Assignee: Genesys Telecommunications Laboratories Incorporated (Genesys Cloud Services Incorporated)
• Inventors: Aravamudhan, Bharath, Duclos, Gregory, Pelemis, Damjan, Konig, Yochai, Zhakov, Vyacheslav, Ristock, Herbert Willi Artur, McGann, Conor, Makagon, Petr
• Primary Examiner(s): Nguyen, Khai N
• Application Number:
  US14/887,310
• Publication Number:
  US 20170111507A1
• Time in Patent Office: 652 Days
• Field of Search: 37921001, 37926501, 37926502, 37926503, 37926504, 37926505, 37926506, 37926507, 37926508, 37926509, 3792651, 37926511, 37926512, 37926513, 37926514, 37926601, 37926602, 37926603, 37926604, 37926605, 37926606, 37926607, 37926608, 37926609, 3792661
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 10/063112 Skill-based matching of a person or a group to a task
• CPC Class Codes: H04L 65/40 Support for services or applications
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/53 using third party service providers
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04M 2203/40 related to call centers
• CPC Class Codes: H04M 2203/401 Performance feedback
• CPC Class Codes: H04M 3/5232 Call distribution algorithms
• CPC Class Codes: H04M 3/5233 Operator skill based call distribution
• CPC Class Codes: H04M 3/5238 with waiting time or load prediction arrangements

Abstract

A system and method for routing interactions to contact center agents. The system is adapted to concurrently identify a plurality of interactions waiting to be routed, and identify a plurality of candidate agents viable for handling the plurality of interactions. The system is also adapted to calculate a predicted wait time associated with each of the candidate agents. For each agent of the plurality of candidate agents, the system is adapted to estimate an expected value to be obtained by routing each of the plurality of the interaction to the agent. The expected value is a function of the predicted wait time. The system is further adapted to assign each of the plurality of the interactions to one of the plurality of candidate agents based on the estimated reward, and signal a routing device for routing each of the plurality of the interactions to the agent assigned to the interaction.

Claims

1. A system for routing interactions to contact center agents, the system comprising:

processor; and

memory, wherein the memory has stored therein instructions that, when executed by the processor, cause the processor to;

concurrently identify a plurality of interactions waiting to be routed;

identify a plurality of candidate agents viable for handling the plurality of interactions;

calculate a plurality of predicted wait times, each associated with a corresponding one of the candidate agents;

for each agent of the plurality of candidate agents, estimate an expected value to be obtained by routing each of the plurality of the interactions to the agent, wherein the expected value is estimated based on the predicted wait time corresponding to the agent;

assign each of the plurality of the interactions to one of the plurality of candidate agents based on the estimated expected value; and

signal a routing device for routing each of the plurality of the interactions to the agent assigned to the interaction.

2. The system of claim 1, wherein the interactions are real-time interactions.

3. The system of claim 1, wherein the predicted wait time is based on a current status of the corresponding agent.

4. The system of claim 3, wherein the status is indicative of whether the agent is available or not to handle the interaction.

5. The system of claim 1, wherein the predicted wait time is based on a predicted customer patience threshold indicative of an amount of time the customer is willing to hold prior to abandoning the interaction.

6. The system of claim 1, wherein the expected value is discounted based on a discount factor, wherein the discount factor is calculated based on the predicted wait time.

7. The system of claim 6, wherein the expected value to be obtained by routing a particular one of the interactions to a particular one of the candidate agents is calculated as being zero if the particular one of the candidate agents is currently unavailable and the wait time exceeds a predicted customer patience threshold.

8. The system of claim 1, wherein the expected value is modeled as a standard normal distribution with an upper confidence bound.

9. The system of claim 1, wherein the expected value is calculated based on profile of the plurality of candidate agents, profile of customers associated with the plurality of the interactions, and intent of each of the plurality of the interactions.

10. The system of claim 9, wherein the profile of each of the plurality of candidate agents includes a dynamically added skill, wherein the dynamically added skill is ignored or mapped to another skill, for calculating the expected value.

11. The system of claim 10, wherein a proficiency level is associated with the skill, wherein the proficiency level is adjusted based on analysis of call transfers for each of the plurality of candidate agents.

12. The system of claim 9, wherein the profile of the plurality of candidate agents includes preference of each of the agents in handling interactions, wherein the instructions further cause the processor to:

generate a routing offer to one or more of the plurality of candidate agents based on the preference of the corresponding agents.

13. The system of claim 1, wherein the plurality of candidate agents and customers associated with the plurality of interactions are modeled as a network of agents and customers, wherein a connection between a node representing one of the candidate agents and a node representing one of the customers is indicative of a fit between the one of the candidate agents and the one of the customers.

14. The system of claim 13, wherein the instructions that cause the processor to assign each of the plurality of interactions to one of the plurality of candidate agents further include instructions that cause the processor to determine how well the customer associated with a particular one of the interactions fits with the one of the plurality of candidate agents.

15. The system of claim 13, wherein the instructions that cause the processor to determine how well the customer fits with the one of the plurality of candidate agents further include instructions that cause the processor to predict sentiment to be expected during the interaction between the customer and the one of the plurality of candidate agents.

16. The system of claim 1, wherein the instructions further cause the processor to:

identify one or more constraints, wherein the plurality of candidate agents are deemed to satisfy the one or more constraints.

17. The system of claim 1, wherein the one or more constraints are skills for handling the plurality of interactions.

18. The system of claim 1, wherein the instructions that cause the processor to assign each of the plurality of the interactions to one of the plurality of candidate agents further cause the processor to:

find assignments that maximize a total expected value from the assignments.